[CF 5685] v5 - Reduce "Var IS [NOT] NULL" quals during constant folding

This branch was automatically generated by a robot using patches from an
email thread registered at:

https://commitfest.postgresql.org/patch/5685

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/CAMbWs4-7D4L=74y5YmgLp5pm0cL_oH+cOWjT1-ZxP_Cc6t+SJQ@mail.gmail.com
Author(s): Richard Guo

Author: Commitfest Bot

contrib/postgres_fdw/expected/postgres_fdw.out

@@ -710,12 +710,12 @@ EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = -c1;          -- Op
    Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE (("C 1" = (- "C 1")))
 (3 rows)
 
-EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c1 IS NOT NULL) IS DISTINCT FROM (c1 IS NOT NULL); -- DistinctExpr
-                                                                 QUERY PLAN                                                                 
---------------------------------------------------------------------------------------------------------------------------------------------
+EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL); -- DistinctExpr
+                                                              QUERY PLAN                                                              
+--------------------------------------------------------------------------------------------------------------------------------------
  Foreign Scan on public.ft1 t1
    Output: c1, c2, c3, c4, c5, c6, c7, c8
-   Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE ((("C 1" IS NOT NULL) IS DISTINCT FROM ("C 1" IS NOT NULL)))
+   Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" WHERE (((c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL)))
 (3 rows)
 
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = ANY(ARRAY[c2, 1, c1 + 0]); -- ScalarArrayOpExpr

contrib/postgres_fdw/sql/postgres_fdw.sql

@@ -352,7 +352,7 @@ EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c3 IS NULL;        -- Nu
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c3 IS NOT NULL;    -- NullTest
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE round(abs(c1), 0) = 1; -- FuncExpr
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = -c1;          -- OpExpr(l)
-EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c1 IS NOT NULL) IS DISTINCT FROM (c1 IS NOT NULL); -- DistinctExpr
+EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE (c3 IS NOT NULL) IS DISTINCT FROM (c3 IS NOT NULL); -- DistinctExpr
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = ANY(ARRAY[c2, 1, c1 + 0]); -- ScalarArrayOpExpr
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c1 = (ARRAY[c1,c2,3])[1]; -- SubscriptingRef
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft1 t1 WHERE c6 = E'foo''s\\bar';  -- check special chars

src/backend/optimizer/plan/initsplan.c

@@ -3048,36 +3048,16 @@ add_base_clause_to_rel(PlannerInfo *root, Index relid,
  * expr_is_nonnullable
  *	  Check to see if the Expr cannot be NULL
  *
- * If the Expr is a simple Var that is defined NOT NULL and meanwhile is not
- * nulled by any outer joins, then we can know that it cannot be NULL.
+ * Currently we only support simple Vars.
  */
 static bool
 expr_is_nonnullable(PlannerInfo *root, Expr *expr)
 {
-	RelOptInfo *rel;
-	Var		   *var;
-
 	/* For now only check simple Vars */
 	if (!IsA(expr, Var))
 		return false;
 
-	var = (Var *) expr;
-
-	/* could the Var be nulled by any outer joins? */
-	if (!bms_is_empty(var->varnullingrels))
-		return false;
-
-	/* system columns cannot be NULL */
-	if (var->varattno < 0)
-		return true;
-
-	/* is the column defined NOT NULL? */
-	rel = find_base_rel(root, var->varno);
-	if (var->varattno > 0 &&
-		bms_is_member(var->varattno, rel->notnullattnums))
-		return true;
-
-	return false;
+	return var_is_nonnullable(root, (Var *) expr, true);
 }
 
 /*

src/backend/optimizer/plan/planner.c

@@ -342,6 +342,7 @@ standard_planner(Query *parse, const char *query_string, int cursorOptions,
 	glob->transientPlan = false;
 	glob->dependsOnRole = false;
 	glob->partition_directory = NULL;
+	glob->rel_notnullatts_hash = NULL;
 
 	/*
 	 * Assess whether it's feasible to use parallel mode for this query. We
@@ -720,6 +721,18 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root,
 	 */
 	transform_MERGE_to_join(parse);
 
+	/*
+	 * Scan the rangetable for relation RTEs and retrieve the necessary
+	 * catalog information for each relation.  Using this information, clear
+	 * the inh flag for any relation that has no children, collect not-null
+	 * attribute numbers for any relation that has column not-null
+	 * constraints, and expand virtual generated columns for any relation that
+	 * contains them.  Note that this step does not descend into sublinks and
+	 * subqueries; if we pull up any sublinks or subqueries below, their
+	 * relation RTEs are processed just before pulling them up.
+	 */
+	parse = root->parse = preprocess_relation_rtes(root);
+
 	/*
 	 * If the FROM clause is empty, replace it with a dummy RTE_RESULT RTE, so
 	 * that we don't need so many special cases to deal with that situation.
@@ -743,14 +756,6 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root,
 	 */
 	preprocess_function_rtes(root);
 
-	/*
-	 * Scan the rangetable for relations with virtual generated columns, and
-	 * replace all Var nodes in the query that reference these columns with
-	 * the generation expressions.  Recursion issues here are handled in the
-	 * same way as for SubLinks.
-	 */
-	parse = root->parse = expand_virtual_generated_columns(root);
-
 	/*
 	 * Check to see if any subqueries in the jointree can be merged into this
 	 * query.
@@ -787,23 +792,6 @@ subquery_planner(PlannerGlobal *glob, Query *parse, PlannerInfo *parent_root,
 
 		switch (rte->rtekind)
 		{
-			case RTE_RELATION:
-				if (rte->inh)
-				{
-					/*
-					 * Check to see if the relation actually has any children;
-					 * if not, clear the inh flag so we can treat it as a
-					 * plain base relation.
-					 *
-					 * Note: this could give a false-positive result, if the
-					 * rel once had children but no longer does.  We used to
-					 * be able to clear rte->inh later on when we discovered
-					 * that, but no more; we have to handle such cases as
-					 * full-fledged inheritance.
-					 */
-					rte->inh = has_subclass(rte->relid);
-				}
-				break;
 			case RTE_JOIN:
 				root->hasJoinRTEs = true;
 				if (IS_OUTER_JOIN(rte->jointype))

src/backend/optimizer/plan/subselect.c

@@ -1458,6 +1458,7 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink,
 	int			varno;
 	Relids		clause_varnos;
 	Relids		upper_varnos;
+	PlannerInfo subroot;
 
 	Assert(sublink->subLinkType == EXISTS_SUBLINK);
 
@@ -1487,6 +1488,24 @@ convert_EXISTS_sublink_to_join(PlannerInfo *root, SubLink *sublink,
 	if (!simplify_EXISTS_query(root, subselect))
 		return NULL;
 
+	/*
+	 * Scan the rangetable for relation RTEs and retrieve the necessary
+	 * catalog information for each relation.  Using this information, clear
+	 * the inh flag for any relation that has no children, collect not-null
+	 * attribute numbers for any relation that has column not-null
+	 * constraints, and expand virtual generated columns for any relation that
+	 * contains them.
+	 *
+	 * Note: we construct up an entirely dummy PlannerInfo for use here.  This
+	 * is fine because only the "glob" and "parse" links will be used in this
+	 * case.
+	 */
+	MemSet(&subroot, 0, sizeof(subroot));
+	subroot.type = T_PlannerInfo;
+	subroot.glob = root->glob;
+	subroot.parse = subselect;
+	subselect = preprocess_relation_rtes(&subroot);
+
 	/*
 	 * Separate out the WHERE clause.  (We could theoretically also remove
 	 * top-level plain JOIN/ON clauses, but it's probably not worth the
@@ -1732,6 +1751,7 @@ convert_EXISTS_to_ANY(PlannerInfo *root, Query *subselect,
 					  Node **testexpr, List **paramIds)
 {
 	Node	   *whereClause;
+	PlannerInfo subroot;
 	List	   *leftargs,
 			   *rightargs,
 			   *opids,
@@ -1791,12 +1811,15 @@ convert_EXISTS_to_ANY(PlannerInfo *root, Query *subselect,
 	 * parent aliases were flattened already, and we're not going to pull any
 	 * child Vars (of any description) into the parent.
 	 *
-	 * Note: passing the parent's root to eval_const_expressions is
-	 * technically wrong, but we can get away with it since only the
-	 * boundParams (if any) are used, and those would be the same in a
-	 * subroot.
-	 */
-	whereClause = eval_const_expressions(root, whereClause);
+	 * Note: we construct up an entirely dummy PlannerInfo to pass to
+	 * eval_const_expressions.  This is fine because only the "glob" and
+	 * "parse" links are used by eval_const_expressions.
+	 */
+	MemSet(&subroot, 0, sizeof(subroot));
+	subroot.type = T_PlannerInfo;
+	subroot.glob = root->glob;
+	subroot.parse = subselect;
+	whereClause = eval_const_expressions(&subroot, whereClause);
 	whereClause = (Node *) canonicalize_qual((Expr *) whereClause, false);
 	whereClause = (Node *) make_ands_implicit((Expr *) whereClause);